Skip to content

Built-in AI Chatbot

The built-in AI chatbot turns connected data into graph work you can inspect. From the Chat page, it can:

  • Inspect catalog metadata, sample rows, profile columns, and probe likely joins.
  • Propose nodes and edges for a graph schema.
  • Apply approved schema changes.
  • Translate natural-language questions into graph queries and explain results.

For a complete hands-on schema-building walkthrough, see Building a Graph with the AI Assistant.

Enable AI Chat

AI Chat requires an AI provider configuration. In a local Docker setup, configure it with environment variables:

environment:
  - AI_ENABLED=true
  - AI_PROVIDER=anthropic
  - AI_API_KEY=${ANTHROPIC_API_KEY:?Set ANTHROPIC_API_KEY for AI Chat}

AI_MODEL is optional. It sets the default model selected by the Chat page. If the Web UI shows a model dropdown, the user's selection is sent with each chat request and overrides that default for the request.

AI_MODELS is also optional. It is a comma-separated list of model IDs to show in the dropdown. Configure it when you want to restrict or customize the choices shown in the Web UI.

You can also configure the API key in Settings → Preferences when the Web UI is available.

Build a graph schema

  1. Connect at least one catalog from the Catalogs page.
  2. Open Chat from the left navigation.
  3. Ask the chatbot to build the graph:
Please inspect my connected catalog and build a graph schema. Profile the tables,
propose a schema, and apply it when the draft is ready.

The chatbot may ask for confirmation before applying schema changes. Review the proposed nodes, edges, source tables, identifiers, and key mappings before approving them. Use auto-confirm only when you are comfortable letting the chatbot apply the proposed graph without per-change approval.

Ask questions about the graph

After a graph schema is active, use Chat as a graph query assistant:

Show the top relationship types connected to User nodes.

Good prompts name the labels, relationships, time windows, filters, or limits you care about. If the chatbot returns no rows, ask it to show which labels and relationships it queried so you can check whether the graph model matches your question.

Use it well

  • Keep the provider API key private. Do not paste secrets into chat messages.
  • Ask for bounded results, such as "top 10" or "limit 20", when exploring data.
  • Review generated queries before turning them into production application logic.
  • Use the chatbot for graph exploration and approved schema changes. Keep unrestricted administrative automation out of normal chat sessions.
  • Use Role-Based Access Control and Row-Level Security when different users should have different access to graph data.